CN109196474A - Distributed operation control in computing system - Google Patents
Distributed operation control in computing system Download PDFInfo
- Publication number
- CN109196474A CN109196474A CN201780030705.XA CN201780030705A CN109196474A CN 109196474 A CN109196474 A CN 109196474A CN 201780030705 A CN201780030705 A CN 201780030705A CN 109196474 A CN109196474 A CN 109196474A
- Authority
- CN
- China
- Prior art keywords
- cluster
- tenant
- service
- application
- execution
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L12/00—Data switching networks
- H04L12/28—Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
- H04L12/46—Interconnection of networks
- H04L12/4641—Virtual LANs, VLANs, e.g. virtual private networks [VPN]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/08—Configuration management of networks or network elements
- H04L41/0895—Configuration of virtualised networks or elements, e.g. virtualised network function or OpenFlow elements
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Debugging And Monitoring (AREA)
- Stored Programmes (AREA)
Abstract
There is described herein the specific embodiments for the computing system, equipment of the control of realization distributed operation, component, module, routine and process in calculating structure.In one embodiment, a kind of method includes the tenant request received at control cluster to the calculating service based on cloud at computing system.This method further includes that the requested application based on cloud for calculating service is configured to supply based on tenant request creation, and to the configuration data for executing the created application of cluster push, to be executed at cluster in the case where the further intervention not from control cluster.
Description
Background technique
Long-range or " cloud " calculates the usual virtual machine set using on remote server rather than local server or individual
Computer handles, manages or store user data.Communication network can using remote server as the node in " grid " into
Row interconnection is to form calculating structure.During operation, the one or more nodes for calculating structure can be with coordination with one another to provide point
Cloth calculates environment, which promotes the execution of various software applications to provide desired cloud service.
Summary of the invention
There is provided this " summary of the invention " is to introduce some concepts in simplified form, these concepts will be in following " tool
It is further described in body embodiment ".This " summary of the invention " be not intended to identify the key feature of theme claimed or
Essential feature is also not intended to the range for limiting theme claimed.
In certain computing systems, calculating structure may include multiple clusters, and each cluster has multiple servers.Each
Multiple servers (for example, five servers) in cluster can be configured as structure controller to monitor and manage in cluster
The operation of other servers.Structure controller can distribute execution task (for example, hosts virtual machine) with the request of customer in response end
And directly interacted with other servers, with configuration, beginning, stopping, migration, monitoring and management trustship on other servers
The virtual machine distributed.However, aforementioned arrangement may limit the number of the server in each cluster.For example, with each group
The number of the server of concentration increase to it is thousands of or even tens of thousands of, structure controller may lack calculating, memory, input/output,
Network, storage or other kinds of resource fully manage the operation of so a large amount of server.
The specific embodiment of disclosed technology is related to through the various operations that will monitor and manage the server in cluster
Certain functions entrust to managed server from structure controller to improve the scalability for calculating the cluster in structure.Specific
In embodiment, control cluster (for example, first group of server) be can receive and the cloud meter including for example one or more virtual machines
Calculate the relevant client request of creation of service (referred to as " tenant ").In the request, client can also be provided and be requested
The relevant associated tenant of tenant (for example, tenant's title, security setting etc.) and service describing are described (for example, code, execution
Configuration and associated data).
In response, control cluster can be with execution cluster communication, and will be executed in executing cluster with instruction has one
Or the application of multiple tasks, to provide service for requested tenant.Two or more examples of application can execute cluster
In different faults domain in, execute in different execution clusters or in other suitable manners, to realize target reliabilities grade
Not.In a particular embodiment, control cluster can be created by realizing stateless and/or stateful role application and/or
Task.Each role may include executable instruction and the associated data for indicating status information.For example, first role can be with
It is configured as tenant and/or the service describing for indicating to receive and store in the network storage library for calculating structure.First role
It can be additionally configured to provide the stored tenant data described to other roles according to request.For example, second role can be with
It is configured as request, tenant and/or service describing is received and handled from first role, there is such as input/output to obtain
Tenant's model of interface, function description, code, execution container etc..In other embodiments, control cluster can also utilize monolithic
Application and/or associated task are created using, multilayer application or other suitable tools.
Once being created, the control cluster can be various relevant to requested tenant to cluster push is executed
The configuration of business, using the component as application.Each task may include processing, memory, storage, network or other suitable types
Resource, application image, the specification for using data or be enough allowing to execute other appropriate informations that cluster executes task.Task is also
It may include indicating on how to execute the data of the strategy of each task relative to each other.
When being activated by control cluster, the execution controller executed in cluster can be based on processing load, Resource Availability
Or other suitable standards are come to each node distributed tasks executed in cluster.On each node, node serve component can
To receive assigned task, and in being locally configured, executing, monitoring and managing assigned application of the task.For example, node
Serviced component can in the health status for locally monitoring performed task, and to execute controller reporting it is any detect ask
Topic.The problem of in response to reported from node, executing controller can be by performed task immigration to for example executing collection
Different server in group, or other remedial measures of application are without the intervention from control cluster.
In this way, several embodiments of disclosed technology can be highly expansible, to provide distributed behaviour in calculating structure
It controls.Different from above-mentioned computing system, control cluster is not interacted with the server executed in cluster not instead of directly, is only created
It creates application and/or the configuration of task and pushes it to execution cluster.It is then possible to execute cluster in task into
Row configuration is executed, monitors and is managed without the intervention from control cluster.Execution cluster usually has more than control cluster
Server.In this way, the function of operation control can highly be distributed in and execute in cluster, and so as to prepare when needed
Good extension is to accommodate Additional servers.
Detailed description of the invention
Fig. 1 is the signal for showing the computing system configured with distributed operation control of the embodiment according to disclosed technology
Figure.
Fig. 2 is that the specific hardware/component software for the computing system for showing Fig. 1 of the embodiment according to disclosed technology shows
It is intended to.
Fig. 3 A-3E is to show according to the embodiment of disclosed technology during the specific operation stage, the computing system of Fig. 1
Specific hardware/component software block diagram.
Fig. 4 A is another computing system configured with distributed operation control for showing the embodiment according to disclosed technology
Schematic diagram.
Fig. 4 B is the computing system of Fig. 4 A during the specific operation stage for showing the embodiment according to disclosed technology
Specific hardware/component software block diagram.
Fig. 5 A-5C is the process for showing the various processes according to the control of the distributed operation of the embodiment of disclosed technology
Figure.
Fig. 6 is suitable for the calculating equipment of the specific components of the computing system in Fig. 1 and 4A.
Specific embodiment
Described below for calculate structure in realize distributed operation control computing system, equipment, component, module,
The specific embodiment of routine and process.In the following description, the detail including component is to provide the spy to disclosed technology
Determine the thorough understanding of embodiment.Those skilled in the relevant art will also be understood that disclosed technology can have other embodiment,
Or it can be practiced in the case where not below with reference to several details of Fig. 1-6 embodiment described.
As used in this article, term " calculate structure " typically refer to have by multiple servers or node it is interconnected amongst one another or
With the computer system of multiple network equipments of external network (for example, internet) interconnection.Calculate structure another example is quilts
Be configured to provide for specific cloud computing facility cloud computation data center (or part thereof).Term " network equipment " typically refers to physics
Networking component.Example network device includes router, interchanger, hub, bridge, load balancer, security gateway or fire prevention
Wall." node " typically refers to be configured as realizing for example one or more virtual machines, virtual router, virtual gateway or other conjunctions
The physical computing devices of suitable virtualization computation module.For example, node may include having to be configured as supporting one or more
The calculation server of the management program of virtual machine.
The calculating network calculated in structure can be divided conceptually in the overlay network realized on bottom-layer network.It " covers
Cover net network " typically refers to the abstract network realized on bottom-layer network and operated above.Bottom-layer network may include that
Multiple physical network devices of this interconnection.On the contrary, overlay network may include one or more virtual networks." virtual network " is logical
Refer to the abstract of a part of the bottom-layer network in overlay network.Virtual network may include the one of referred to as " tenant's website "
A or multiple virtual endpoints, tenant's website used respectively by client with access virtual network and it is associated calculate, storage or
Other suitable resources.Tenant's website can be with trustship one or more tenant's example, for example, virtual with corresponding tenant's type
Machine.Virtual network can interconnect multiple tenant's examples on the different nodes for calculating structure.Virtual network in overlay network is set
It is standby can by with one or more networks routing along one or more physical network devices in bottom-layer network respectively
Corresponding virtual link is connected to each other.
The term " role " being also used herein typically refers to isolated, the independent calculating and state executed with single thread
Unit.Role can simultaneously and independently execute in concurrent or distributed system.Role can communicate with one another, and can create
Build additional role.For example, role can by using such as request response modes exchange asynchronous message and operating system or with
Other roles interaction.
As used in this article, term " application " typically refers to respectively to be configured as to execute specific function and can be
The set of the composition service or task that are executed in distributed cloud computing structure." service " or " task " typically refers to be configured as solely
Other services or task for standing in same application and be executed to perform the component software of desired function.In specific embodiment
In, configuration and/or suitable data when service or task may include computer executable instructions, operation.In other embodiments
In, service or task can also include implementation strategy, performance parameter, type, version and/or other suitable information.
In addition, as used in this article, term " control cluster " typically refers to be configured as based on received from client
Tenant request creates the computing system of the application that can be performed by execution cluster.Term " executing cluster " typically refers to be configured as
The computing system of the created application of execution and the result that requested tenant is provided to client.It controls cluster and executes collection
Group can include one or more virtual machines and/or physical server interconnected amongst one another.In a particular embodiment, cluster is controlled
It can be separated with associated execution cluster.In other embodiments, control cluster can be common with associated execution cluster
Positioning.
In some computing systems, the particular server calculated in structure can be configured as structure controller, with monitoring
With the operation for managing other servers.Structure controller can distribute execution task (for example, hosts virtual machine) and directly with
Other servers interaction, with configuration, beginning, stopping, migration or otherwise monitoring and management trustship on other servers
The virtual machine distributed.However, this arrangement may limit the number of the server in cluster.For example, with server
Number increase to it is thousands of or even tens of thousands of, structure controller may rapidly depleting available resources it is so a large amount of fully to manage
The operation of server.
Several embodiments of disclosed technology can be by being converted to specific application for tenant request to have a large amount of sections
It is executed in the execution cluster of point, to improve the scalability calculated in structure.In this way, the specific function of traditional structure controller can
To entrust to the node executed in cluster.For example, execution can be configured, execute, monitoring or otherwise managing by executing cluster
The operation of server in cluster.Therefore, different from conventional computing system, the not direct node with execution cluster of control cluster
Interaction is with the various operations of management node.As a result, executing cluster can more easily extend than conventional computing system, such as following ginseng
Examine what Fig. 1-6 was more fully described.
Fig. 1 is the computing system for being configured for distributed operation control for showing the embodiment according to disclosed technology
100 schematic diagram.As shown in Figure 1, computing system 100 may include interconnection multiple client 101, control cluster 126, Yi Jiyi
A or multiple bottom-layer networks 108 for executing cluster 128 and calculating structure with formation.Two execution clusters are shown for purpose of explanation
128, but computing system 100 may include any suitable number of execution cluster 128.In addition, for clarity, Fig. 1 only shows
The details of an execution cluster 128 is gone out.The configuration that other execute the execution cluster that cluster 128 can have and be shown specifically is big
Cause similar or different configuration.Although showing the specific components of computing system 100 in Fig. 1, in other embodiments, meter
Calculation system 100 can also include additional and/or different component.For example, in a particular embodiment, computing system 100 can be with
Including network storage equipment, public utility infrastructure and/or other suitable component (not shown).
As shown in Figure 1, bottom-layer network 108 may include interconnection customer end 101, control cluster 126 and execution cluster 128
One or more network equipments 112.Bottom-layer network 108 may include multiple network equipments 112, the multiple network equipment 112
It is operatively coupled each other and is interconnected into calculating structure will control cluster 126 and execute cluster 128.The example of the network equipment 112
It may include router, interchanger, firewall, load balancer or other suitable networking components.Although for illustration purposes
Specific connection scheme is shown in FIG. 1, but in other embodiments, the network equipment 112 can be with layering, plane, " net
Lattice " or other suitable topological structures and be operatively coupled.
Executing cluster 128 may include the multiple nodes 106 being operatively coupled each other via bottom-layer network 108 and executes
Controller 130.In a particular embodiment, node 106 can respectively include processor, physical server or several physical services
Device.In other embodiments, node 106 can also include virtual server or several virtual servers.Node 106 can be by group
It is made into rack, Free Region, group, set or other suitable divisions.For example, in the shown embodiment, node 106 is grouped into
Three racks of the first, second, and third rack 107a-107c are respectively identified as, they are operatively coupled to corresponding net
Network equipment 112a-112c.Then, network equipment 112a-112c can be operatively coupled to the other network equipment 112 with shape
At the computer network for allowing the communication between node 106 and execution controller 130.In a particular embodiment, have corresponding
Each rack 107a-107c of network equipment 112a-112c can form different failure domains.In other embodiments, multiple
Rack 107a-107c can share single network equipment 112, or can have other suitable topologys.
Node 106 can respectively be configured as providing calculating, storage and/or other suitable cloud computings to tenant 101
Facility.For example, such as in greater detail below with reference to Fig. 2, one of node 106 may include starting and keep one or more empty
The component (as shown in Figure 2) of quasi- machine 144.Then, client 101 can use started virtual machine 144 to execute calculating, lead to
Letter, content distribution and/or other suitable operations.In a particular embodiment, one of node 106 can be with trustship multiple client
101 virtual machine 144.For example, one of node 106 can correspond respectively to three void of each client 101a-101b with trustship
Quasi- machine 144.
Execute the operation that controller 130 can be configured as monitoring and management executes the node 106 in cluster 128.For example,
In a particular embodiment, execute controller 130 can be configured as distribution will at various nodes 106 dispose application and/or
Service.The execution of application and/or service, the health status of node or other operating parameters can also be monitored by executing controller 130.
In the case where detecting operational issue, execute controller 130 can be configured as execute failure transfer and node 106 it
Between the routing of consistent message is provided.It may include western refined by the State of Washington for being adapted for carrying out the example control system of controller 130
The Amazon Web Service controller that the Amazon.com of figure is provided or the Microsoft by Redmond city
The Azure structure controller that Corporation is provided.The reality for executing controller 130 is more fully described below with reference to Fig. 3 A-3E
Apply the specific components of example.
Control cluster 126, which can be configured as from client 101, receives tenant request, and being created based on this will be by holding
The application and service that row cluster 128 executes.In a particular embodiment, control cluster 126 can be directly into execution cluster 128
One or more nodes 106 distribute the execution of created application.In other embodiments, control cluster 126, which can permit, holds
Line control unit 130 distributes the deployment of created application and/or service.In a further embodiment, control cluster 126 can be to
Such as other in different data center execute cluster (not shown) rather than execute cluster 128 and distribute created application.Under
The exemplary components and operation of control cluster 126 are more fully described with reference to Fig. 3 A-3E for face.
In operation, one or more of client 101 can be transmitted via bottom-layer network 108 to control cluster 126
Tenant request.Tenant request may include the cloud facility of suitable trustship, the virtual machine of such as trustship, network service and/or its
His suitable facility.In response, control cluster 126, which can create, to be executed by execution cluster 128 to provide requested rent
The one or more application of the example at family and associated service.Using can respectively include one or more service, these
Configuration and/or suitable data when service can respectively include computer executable instructions, operation.Then, cluster 126 is controlled
It can be to the configuration for executing the push of cluster 128 application and/or service.
In response to receiving the configuration of application and/or service from control cluster 126, executes in cluster 128 and execute control
Device 130 can distribute each application and/or service to the one or more nodes 106 executed in cluster 128.In each node
At 106, the Life Cycle of the example of application and/or service can be managed in response to the received application of institute and/or service, node 106
Phase, without the further intervention from control cluster 126.For example, node 106 can configure on node 106, start, stop
Only, it migrates or one or more tenant's containers such as otherwise manage virtual machine 144." tenant as used in this article
Container " is typically referred to be configured as executing application or be serviced to provide the software of requested tenant or part thereof of example and hold
Device.Example tenant's container may include virtual machine, Docker container or other suitable component softwares.During operation, node
106 can also be to execution 130 reporting operations parameter of controller or problem.If detecting failure in a node 106 or asking
Topic, then executing controller 130 can cause the virtual machine 144 of trustship to be migrated to another node 106 executed in cluster 128.
In this way, different from conventional computing system, control cluster 126 is not handed over the node 106 executed in cluster 128 directly
Mutually with the various operations of configuration, monitoring or management node 106.On the contrary, such function is entrusted to and executes control by control cluster 126
Device 130 or node 106 processed.Therefore, control cluster 126 can accommodate more obvious than in conventional computing system in executing cluster 128
The node 106 of greater number.
Fig. 2 is the example nerve of a covering realized on the bottom-layer network 108 in Fig. 1 shown according to the embodiment of disclosed technology
The schematic diagram of network 108'.In Fig. 2, for clarity, the specific components of the bottom-layer network 108 of Fig. 1 are illustrated only.Such as Fig. 2 institute
Show, first node 106a and second node 106b each may include processor 132, the memory being operatively coupled each other
134 and input output assembly 136.Processor 132 may include microprocessor, field programmable gate array and/or other are suitable
Logical device.Memory 134 may include being configured as storing from the received data of processor 132 and processor 132
Instruction (for example, instruction for executing method below with reference to Fig. 5 discussion) volatibility and/or non-volatile media (for example,
ROM;RAM, magnetic disk storage medium;Optical storage medium;Flash memory device and/or other suitable storage mediums) and/or other classes
The computer readable storage medium of type.Input output assembly 136 may include be configured as receive from operator and/or from
The input of dynamic software controller (not shown) and provide it the display of output, touch screen, keyboard, mouse, printer and/or
The input-output apparatus of other suitable types.
The memory 134 of first node 106a and second node 106b may include that can be performed by processor 132 to cause
Each processor 132 provides management program 140 (being individually identified as the first management program 140a and the second management program 140b)
Instruction and other suitable component (not shown).Management program 140 can respectively be configured as starting, monitoring, terminate and/or
One or more virtual machines 144 of tenant's website 142 are otherwise organized into local management.For example, as shown in Fig. 2,
First node 106a can provide the first management program for managing first tenant's website 142a and second tenant's website 142b respectively
140a.Second node 106b can provide the second pipe for managing first tenant's website 142a' and second tenant's website 142b' respectively
Manage program 140b.Management program 140 can be software, firmware or hardware component.Tenant's website 142 each may include for spy
Determine the multiple virtual machines 144 or other suitable tenant's examples of tenant's (not shown).For example, first node 106a and second node
106b can trustship the first tenant 101a (Fig. 1) tenant's website 142a and 142a'.First node 106a and second node
106b can trustship the second tenant 101b (Fig. 1) tenant's website 142b and 142b'.Each virtual machine 144 can execute phase
Operating system, middleware and/or the application answered.
Also as shown in Fig. 2, computing system 100 may include have across multiple main frames 106 interconnect tenant's website 142a and
The overlay network 108' of one or more virtual networks 146 of 142b.For example, the first virtual network 142a interconnects first node
The first tenant's website 142a and 142a' at 106a and second node 106b.Second virtual network 146b interconnects first node
The second tenant's website 142b and 142b' at 106a and second node 106b.Although single virtual network 146 is shown as corresponding to
In tenant's website 142, but in other embodiments, multiple 146 (not shown) of virtual network can be configured as correspondence
In single tenant's website 146.
Even if virtual machine 144 is located on different hosts 106, the virtual machine 144 in virtual network 146 can also be the bottom of via
Layer network 108 (Fig. 1) communicates with one another.The communication of each virtual network 146 can be isolated with other virtual networks 146.In spy
Determine in embodiment, can permit communication by security gateway or otherwise in a controlled manner from a virtual network 146 across
More arrive another virtual network.Virtual network address can correspond to one of the virtual machine 144 in specific virtual network 146.Therefore,
Identical one or more virtual network address can be used in different virtual networks 146.Example virtual network address can wrap
Include IP address, MAC Address and/or other suitable addresses.
Fig. 3 A-3E is the embodiment shown according to disclosed technology, the computing system of Fig. 1 during the specific operation stage
100 specific hardware/component software block diagram.In Fig. 3 A-3E and other figures herein, each component software, object,
Class, module and routine can be the computer that source code is written as with C, C++, C#, Java and/or other suitable programming languages
Program, process or process.Component can include but is not limited to one or more modules, object, class, routine, attribute, process, line
Journey, executable file, library or other assemblies.Component can be source or binary form.Component may include the source before compiling
The various aspects (for example, class, attribute, process, routine) of code, the binary cell (for example, library, executable file) of compiling or
The workpiece (for example, object, process, thread) that person instantiates and uses at runtime.In a particular embodiment, described below each
Kind component and module can be realized with role.In other embodiments, can also use monolithic application, multilayer application or other
Suitable component realizes the generation of application and/or related service.
Component in system can use different forms in system.As an example, including first assembly, second
The system of component and third component can include but is not limited to following system, which includes the attribute as source code form
First assembly compiles second component in library as binary system and as the third component of the thread created at runtime.It calculates
Machine program, process or process can be compiled into object, centre or machine code, and be presented for by individual calculus
Machine, network server, laptop computer, smart phone and/or other suitable one or more processors for calculating equipment
It executes.Equally, component may include hardware circuit.It will be appreciated by those of ordinary skill in the art that hardware is considered stone
The software of change, and software is considered liquefied hardware.Only as an example, the software instruction in component can be by
It is burnt to programmable logic array circuit, or can be designed as the hardware circuit with integrated circuit appropriate.Equally, firmly
Part can be simulated by software.The various realizations of source, middleware and/or object code and associated data, which can store, to be calculated
In machine memory, including read-only memory, random access memory, magnetic disk storage medium, optical storage media, flash memory device and/
Or other suitable computer readable storage mediums, except transmitting signal.
As shown in Figure 3A, control cluster 126 may include the interface module 133 being operatively coupled each other, distributor group
Part 135 and control assembly 137.As described above, control cluster 126 may include one or more physics or virtual interconnected amongst one another
Server.In this way, in a particular embodiment, the example for controlling the shown component of cluster 126 can be located at single physical or virtual
On server.In other embodiments, the example of aforementioned components can be distributed on multiple physics or virtual server.In addition
Embodiment in, the repetition example of at least some aforementioned components can also be distributed on multiple physics or virtual server, with
Such as targeted usability is provided.
Interface module 126 can be configured as from the request that the reception of client 101 is inputted as user and describe 150.In spy
Determine in embodiment, request description 150 may include tenant's description and service describing.Tenant's description may include indicating tenant's name
Title, security setting, network application indicates and the data of other appropriate informations.Service describing may include for example with requested rent
The relevant program code in family, configuration and associated data.
Then, interface module 126, which can be configured as, describes 150 for received request and is transmitted to dispenser assembly 135
With control assembly 137 to be further processed.In the available spy of multiple examples of dispenser assembly 135 or control assembly 137
Determine in embodiment, interface module 126 may include selecting the particular instance of aforementioned components to be further processed received request
The stateless distributor of description 150.In other embodiments, interface module 133 can also include for by received request
150 transmission of description is transferred to other the suitable components for controlling the other assemblies of cluster 126.
In a particular embodiment, dispenser assembly 135 can be configured as the class of position based on client 101, operation
Type, the availability for executing cluster or other suitable information and distributed special in response to being inputted to the user for executing one of cluster
Fixed operation.In figs. 3 a-3e, a selected execution cluster 128 is illustrated only.In other embodiments, dispenser assembly
135 can distribute the copy of same operation to multiple execution clusters 128 in computing system 100.In a further embodiment, divide
It can be additionally configured to device assembly 135 to 106 batch operation of specific node executed in cluster 128.
Control assembly 137, which can be configured as, to be applied based on from the received request of interface module 133 description 150 to generate,
To be executed in executing cluster 128.As shown in Figure 3A, control assembly 137 may include image module 162, tenant's module 164,
Tenant's model module 166 and service module 168.Image module 162, which can be configured as, describes 150 conducts for received request
Service describing role 171 (being shown as SD 171 in figure 3 a) and tenant describe role's 172 (being shown as TD 172 in figure 3 a)
Record storage is in the image library (not shown) of control cluster 126.Image module 162 can be additionally configured to according to request via
Such as the service stored and tenant are described 171 and 172 and are supplied to other modules by API or other suitable interfaces.
Tenant's model module 166, which can be configured as, to be based on retouching from the received service describing 171 of image module 162 and tenant
172 are stated to create tenant's model 174.In a particular embodiment, tenant's model 174 may include input/output interface specification,
Configuration information (such as setting, covering and communication channel), the computer-executable code that can be executed, information of container are (such as empty
Quasi- machine) and other suitable information.
As shown in Figure 3B, it is based on tenant's model 174, tenant's module 164 can be created to be described corresponding to received request
And cluster 128,176 (being shown as app 176 in figure 3 a) of application of middle execution can executed.The application 176 created
It may include one or more services as the component part for applying 176.For example, as shown in Figure 3 C, service module 168 can be created
Build multiple services 178 associated with applying 176.In the shown embodiment, for purposes of illustration, three services are shown
178.In other embodiments, service module 168 can be configured as any suitable number of service 178 of creation.
Also as shown in Figure 3 C, executing controller 130 may include that monitoring and management node 106 (are shown as node 106a-
The executive module 131 of operation 106c).For example, in a particular embodiment, control cluster 126 can refer to controller 130 is executed
Show to be assigned to using the execution of 176 example and executes cluster 128.In response, executive module 131 can be for using 176 wounds
Placeholder is built, and waits and applies 176 relevant other information.
As shown in Figure 3D, the service 178 created can be transferred to by control cluster 126 executes controller 130 to be used for
It executes.In response, executive module 131 can be configured as based on processing load, resource type or other suitable standards to
Each node 106 in cluster 128 is executed to distribute service 178.For example, in the shown embodiment, service 178a-178c difference
It is distributed to node 106a-106b.In other embodiments, service 178 can be distributed in other suitable manners.
After receiving distributed service 178a-178c, each node 106a-106c can be with the service that is distributed
178a-178c interaction, for example, being interacted with management program 107 (Fig. 2), with holding for configuration, starting and monitoring service 178a-178c
Row, to start and manage tenant's container (for example, virtual machine).During operation, node 106a-106c can be monitored performed
Service the execution parameter and condition of 178a-178c.Node 106a-106c can report any monitored to controller 130 is executed
Execution parameter and condition.In the case where executive problem, executing controller 130 can be migrated or using other remedial measures.
For example, as shown in FIGURE 3 E, in the case where node 106b report node failure or other problems, executing controller 130 can draw
It plays service 178b and moves to node 106c to continue to execute.
Although executing cluster 128 is shown in Figure 1 for having flat topology, in other embodiments, cluster is executed
128 can have additional level.For example, as shown in Figure 4 A, executing cluster 128 may include multiple junior's clusters 109, under each
Grade cluster 109 has cluster controller 129 (being shown as cluster controller 129a-129c).In operation, as shown in Figure 4 B, it holds
Line control unit 130 can be distributed using 174 and/or service 178 to select junior's cluster 109.Successively, junior's cluster 109 is every
Executive module 131 in a cluster controller 129 can be downward based on processing load, resource type or other suitable standards
Each node 106 in grade cluster assigns distributed service 178.
Fig. 5 A is the flow chart for showing the distributed operation control process 200 according to the embodiment of disclosed technology.In spy
Determine in embodiment, process 200 can be realized in the control cluster 126 of the computing system 100 of Fig. 1, to create new tenant, delete
Except existing tenant or the existing tenant of update/modification.In other embodiments, process 200 can also have for other conjunctions
It is realized in the similar or different component of suitable function and/or other computing systems of configuration.
As shown in Figure 5A, process 200 may include receiving from client to the rent based on cloud for calculating service in the stage 202
Family request.As above with reference to discussing Fig. 1, tenant request may include service describing, tenant's description or other suitable letters
Breath.Then, process 200 may include in the received tenant request of the processing of stage 204 institute.In a particular embodiment, processing is connect
The tenant request of receipts may include that the received service describing of institute, tenant's description or other suitable information are stored in calculating structure
In image library in.In other embodiments, the received tenant request of processing institute can also include being retouched based on the received service of institute
It states, tenant's description or other suitable information generate tenant's model.
Then, process 200 may include that can be held based on such as tenant's model for requested tenant configuration in the stage 206
Row application.In a particular embodiment, application can be performed may include one or more services, as described above with reference to Figure 1.
In other embodiments, it can also include indicating the data of the implementation strategy about one or more service that application, which can be performed,.Example
Such as, implementation strategy can specify two different services and cannot execute on single failure domain, need to continuously perform, or with it
He executes suitable mode.Then, process 200 may include being pushed to the configuration of executable application and associated service to hold
Row cluster is to execute.
Fig. 5 B is the flow chart for showing the process 210 of the execution application based on cloud according to the embodiment of disclosed technology.
As shown in Figure 5 B, process 210 may include receiving the configuration of executable application in the stage 212.Process 210 can also be included in rank
214 processing application of section is for execution.In a particular embodiment, using may include multiple services.Therefore, processing application can wrap
It includes based on implementation strategy for example associated with service and is executed to the various services of one or more nodes distribution.Processing is answered
With that can also include configuration, the service for initiating or stopping various distribution, for example, at each node.
Process 210 can also be included in the stage 216 in local management application execution.For example, as shown in Figure 5 C, management application
Execution may include monitoring application execution in the stage 222.Then, process 216 may include being used to determine whether to detect problem
The decision stage of (for example, node failure).In response to confirmly detecting problem, process 216 may include applying remedial measure, all
The execution of service is such as moved into another node, reset node or other suitable measures.It is asked in response to determining to be not detected
It inscribes, application execution is monitored at 216 return stage 222 of process.
Fig. 6 is suitable for the calculating equipment 300 of the specific components of the computing system 100 in Fig. 1.For example, calculating equipment 300
It may adapt to the node in the node 106 executed in cluster 128 or control cluster 126 of Fig. 1.In very basic configuration
In 302, calculating equipment 300 may include one or more processors 304 and system storage 306.Memory bus 308 can be with
For the communication between processor 304 and system storage 306.
According to desired configuration, processor 304 can be any type, including but not limited to microprocessor (μ P), micro-control
Device (μ C) processed, digital signal processor (DSP) or any combination thereof.Processor 304 may include that one or more levels high speed is slow
Deposit (such as on-chip cache 310 and second level cache 312), processor core 314 and register 316.Example processor core
314 may include arithmetic logic unit (ALU), floating point unit (FPU), Digital Signal Processing core (DSP core) or any combination thereof.
Example memory controller 318 can also be used together with processor 304, or in some implementations, Memory Controller 318
It can be the internal part of processor 304.
According to desired configuration, system storage 306 can be any type, including but not limited to volatile memory
(RAM), nonvolatile memory (ROM, flash memory etc.) or any combination thereof.System storage 306 may include behaviour
Make system 320, one or more application 322 and program data 324.As shown in fig. 6, operating system 320 may include for managing
Manage the management program 140 of one or more virtual machines 144.The basic configuration 302 of this description is in Fig. 6 by inner dotted line
Those components are shown.
Calculating equipment 300 can have supplementary features or function and for promoting basic configuration 302 and any other to set
The additional interface of the standby communication between interface.For example, bus/interface controller 330 can be used for promoting basic configuration 302 with
Via the communication of memory interface bus 334 between one or more data storage devices 332.Data storage device 332 can be
Movable memory equipment 336, non-removable storage device 338 or combinations thereof.Removable Storage and non-removable storage device
Example includes the disk units such as floppy disk drive and hard disk drive (HDD), such as compact disk (CD) driver or number
The CD drives such as universal disc (DVD) driver, solid state drive (SSD) and tape drive etc..Exemplary computer storage is situated between
Matter may include times of the information such as computer readable instructions, data structure, program module or other data for storage
What method or technique come realize volatile and non-volatile, removable and irremovable medium.Term " computer-readable storage
Medium " or " computer readable storage devices " do not include transmitting signal and communication media.
System storage 306, movable memory equipment 336 and non-removable storage device 338 are computer-readable storages
The example of medium.Computer readable storage medium include but is not limited to RAM, ROM, EEPROM, flash memory or other memory technologies,
CD-ROM, digital versatile disc (DVD) or other optical memory, cassette, tape, magnetic disk storage or other magnetic storage apparatus
Or any other medium that can be used for storing information needed and can be accessed by calculating equipment 300.Any such meter
Calculation machine readable storage medium storing program for executing can be a part for calculating equipment 300.Term " computer readable storage medium " does not include propagating
Signal and communication media.
Calculating equipment 300 can also include for promoting via bus/interface controller 330 from various interface equipment (examples
Such as, output equipment 342, peripheral interface 344 and communication equipment 346) to basic configuration 302 communication interface bus 340.Example
Output equipment 342 is various via one or more ports A/V 352 and display or loudspeaker etc. including can be configured as
The graphics processing unit 348 and audio treatment unit 350 of external device communication.Exemplary peripheral interface 344 includes that can be configured
For via one or more ports I/O 358 with such as input equipment (for example, keyboard, mouse, pen, voice-input device, touch
Input equipment etc.) or the external device communications such as other peripheral equipments (for example, printer, scanner etc.) serial interface controller
354 or parallel interface controller 356.Example communication device 346 includes that can be arranged to promote to communicate via one or more
The network controller 360 that port 364 is communicated by network communication link with other one or more calculating equipment 362.
Network communication link can be an example of communication media.Communication media usually can be by computer-readable finger
Enable, other data (such as carrier wave or other transmission mechanisms) in data structure, program module or modulated data signal are implemented,
It and may include any information transmitting medium." modulated data signal ", which can be, to enable in the signal carry out information
The mode of coding is set or changed the signal of one or more feature.As an example, not a limit, communication media can wrap
Include the wired mediums such as cable network or direct wired connection and such as acoustics, radio frequency (RF), microwave, infrared (IR) and its
The wireless mediums such as his wireless medium.Term computer-readable medium used herein may include that storage medium and communication are situated between
Matter.
Calculating equipment 300 may be implemented as such as cellular phone, personal digital assistant (PDA), personal media player
Equipment, wireless network watch device, personal ear speaker device, special equipment or the mixing apparatus including any of above function etc. are small-sized
A part of portable (or mobile) electronic equipment.Equipment 300 is calculated to be also implemented as including laptop computer and non-knee
The personal computer of laptop computer configuration.
From the foregoing it will be appreciated that for purposes of illustration, the specific embodiment of the disclosure already described herein,
But various modifications can be carried out in the case of not departing from the present disclosure.In addition, in addition to or replace other embodiments element, one
Many elements of a embodiment can be combined with other embodiments.Therefore, except as by the appended claims, this technology is unrestricted
System.
Claims (10)
1. a kind of method for the distributed operation control in the computing system for being configured to supply cloud computing service, described
Computing system has control cluster and executes cluster, which comprises
The tenant request for the calculating facility based on cloud at the computing system is received at the control cluster;
Based on the received tenant request of institute, tenant's mould associated with the requested calculating facility based on cloud is generated
Type, tenant's model include at least one in input/output interface, function description, code or execution container;
It is configured to supply the requested application based on cloud for calculating facility based on tenant's model creation, it is described to answer
With including one or more service, one or more of services configured when separately including computer executable instructions, operation and
Data;And
The configuration data of the application created to the execution cluster push, with not from it is described control cluster into
It is performed at the execution cluster in the case where one step intervention, so that the control cluster be allowed to adapt to additional tenant request.
2. according to the method described in claim 1, wherein:
The tenant request includes service describing and tenant's description;
The service describing includes code, executes configuration and associated data;
Tenant's description includes tenant's title and security setting;And
Generating tenant's model includes describing to generate tenant's model based on the service describing and the tenant.
3. according to the method described in claim 1, further include indicate it is described execution cluster based on pushed created described in
The configuration data of application starts the example of the application created.
4. according to the method described in claim 1, further include indicate it is described execution cluster based on pushed created described in
The configuration data of application starts the example of the application created, and by the example of the application created
It executes control and entrusts to the execution cluster.
5. according to the method described in claim 1, further include indicate it is described execution cluster based on pushed created described in
The configuration data of application starts the example of the application created, and by the example of the application created
At least one in configuring, starting or stopping entrusts to the execution cluster.
6. according to the method described in claim 1, wherein:
The execution cluster is the first execution cluster;
The computing system further includes the second execution cluster;And
The method also includes indicating that the first execution cluster and the second execution cluster are each created based on what is pushed
The configuration data for the application built starts the example of the application created.
7. the multiple service divides according to the method described in claim 1, wherein creating the application includes creating multiple services
It Bao Han not be by configuration, data and execution when the computer executable instructions followed during execution by the execution cluster, operation
Strategy, the implementation strategy of a service are serviced relative to other of the application created.
8. the multiple service divides according to the method described in claim 1, wherein creating the application includes creating multiple services
It Bao Han not be by configuration, data and execution when the computer executable instructions followed during execution by the execution cluster, operation
Strategy, implementation strategy of one of service indicate the service by with another service in service in the execution cluster
It is executed on different nodes.
9. the method that the distributed operation in a kind of computing system for being configured to supply cloud computing service controls, described
Computing system has control cluster and executes cluster, which comprises
It receives from the control cluster by the configuration data of the application executed at the execution cluster, the application is configured as
The calculating facility based on cloud of client request is provided, and wherein the application includes one or more services, it is one
Or multiple services separately include computer executable instructions, operation when configuration and data;
To the example of the one or more of services of each node deployment for executing cluster to be used to execute;And
Indicate that each node is being locally configured, is starting in the case where the further intervention not from the control cluster
With the example disposed for monitoring one or more of services, to provide the calculating based on cloud of the client request
Facility.
10. according to the method described in claim 9, further include:
Receive the monitoring operation parameter of the example of the service executed on each node;
Operational issue is determined whether there is based on the received operating parameter of institute;And
In response to determining there are operational issue, in the execution cluster in the case where intervention not from the control cluster
It is interior to apply remedial measure.
Applications Claiming Priority (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US15/157,196 US10153941B2 (en) | 2016-05-17 | 2016-05-17 | Distributed operational control in computing systems |
US15/157,196 | 2016-05-17 | ||
PCT/US2017/032303 WO2017200853A1 (en) | 2016-05-17 | 2017-05-12 | Distributed operational control in computing systems |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109196474A true CN109196474A (en) | 2019-01-11 |
CN109196474B CN109196474B (en) | 2021-12-03 |
Family
ID=58745472
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201780030705.XA Active CN109196474B (en) | 2016-05-17 | 2017-05-12 | Distributed operation control in a computing system |
Country Status (4)
Country | Link |
---|---|
US (1) | US10153941B2 (en) |
EP (1) | EP3458958A1 (en) |
CN (1) | CN109196474B (en) |
WO (1) | WO2017200853A1 (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111124692A (en) * | 2020-01-02 | 2020-05-08 | 神州数码融信软件有限公司 | Service request processing system |
CN113905083A (en) * | 2021-10-15 | 2022-01-07 | 上海商汤临港智能科技有限公司 | User code operation method and device, electronic equipment and storage medium |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10013265B2 (en) | 2016-06-23 | 2018-07-03 | International Business Machines Corporation | Management of container host clusters |
US10387198B2 (en) | 2016-08-11 | 2019-08-20 | Rescale, Inc. | Integrated multi-provider compute platform |
US10193762B2 (en) | 2016-08-11 | 2019-01-29 | Rescale, Inc. | Dynamic optimization of simulation resources |
US20180060132A1 (en) * | 2016-09-01 | 2018-03-01 | Amazon Technologies, Inc. | Stateful resource pool management for job execution |
EP3549018B1 (en) * | 2016-11-29 | 2021-04-07 | Telefonaktiebolaget LM Ericsson (publ) | Distribution of resources among actor instances |
CA3055987C (en) | 2017-03-23 | 2023-03-14 | Dh2I Company | Highly available stateful containers in a cluster environment |
US11329885B2 (en) * | 2018-06-21 | 2022-05-10 | International Business Machines Corporation | Cluster creation using self-aware, self-joining cluster nodes |
CN111130820B (en) * | 2018-10-30 | 2023-05-30 | 阿里巴巴集团控股有限公司 | Cluster management method and device and computer system |
US11010084B2 (en) * | 2019-05-03 | 2021-05-18 | Dell Products L.P. | Virtual machine migration system |
US20200403985A1 (en) * | 2019-06-19 | 2020-12-24 | Hewlett Packard Enterprise Development Lp | Method for federating a cluster from a plurality of computing nodes |
US11240345B2 (en) | 2019-06-19 | 2022-02-01 | Hewlett Packard Enterprise Development Lp | Method for deploying an application workload on a cluster |
CN111309447B (en) * | 2020-03-16 | 2023-08-25 | 优刻得科技股份有限公司 | Container dispatching method and device |
CN111309448B (en) * | 2020-03-16 | 2022-07-29 | 优刻得科技股份有限公司 | Container instance creating method and device based on multi-tenant management cluster |
US11836523B2 (en) * | 2020-10-28 | 2023-12-05 | Red Hat, Inc. | Introspection of a containerized application in a runtime environment |
US11550633B2 (en) * | 2020-10-31 | 2023-01-10 | Nutanix, Inc. | Intra-footprint computing cluster bring-up |
CN112395091A (en) * | 2020-11-24 | 2021-02-23 | 上海商汤智能科技有限公司 | Cloud service request response method and device, electronic equipment and storage medium |
CN115250276A (en) * | 2021-04-27 | 2022-10-28 | 北京同邦卓益科技有限公司 | Distributed system and data processing method and device |
US11900172B2 (en) | 2021-07-30 | 2024-02-13 | Nutanix, Inc. | Computing cluster bring-up on public cloud infrastructure using expressed intents |
CN114866570A (en) * | 2022-04-18 | 2022-08-05 | 北京快乐茄信息技术有限公司 | Information processing method and device, electronic equipment and storage medium |
Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100050172A1 (en) * | 2008-08-22 | 2010-02-25 | James Michael Ferris | Methods and systems for optimizing resource usage for cloud-based networks |
CN102110041A (en) * | 2011-03-15 | 2011-06-29 | 浪潮(北京)电子信息产业有限公司 | System and method for monitoring storage space of distributed file system |
US20120233315A1 (en) * | 2011-03-11 | 2012-09-13 | Hoffman Jason A | Systems and methods for sizing resources in a cloud-based environment |
CN102708000A (en) * | 2012-04-19 | 2012-10-03 | 北京华胜天成科技股份有限公司 | System and method for realizing energy consumption control through virtual machine migration |
CN102722413A (en) * | 2012-05-16 | 2012-10-10 | 上海兆民云计算科技有限公司 | Distributed resource scheduling method for desktop cloud cluster |
CN102915331A (en) * | 2011-09-12 | 2013-02-06 | 微软公司 | Coordination engine for cloud selection |
CN103034536A (en) * | 2011-12-12 | 2013-04-10 | 微软公司 | Usability for improving stateful applications |
US20130262556A1 (en) * | 2012-03-28 | 2013-10-03 | Microsoft Corporation | Enhanced Computer Cluster Operation Using Resource Allocation Requests |
US20140032531A1 (en) * | 2012-07-25 | 2014-01-30 | Cisco Technology, Inc. | System and method for a service metering framework in a network environment |
WO2014034199A1 (en) * | 2012-08-30 | 2014-03-06 | 株式会社ソニー・コンピュータエンタテインメント | Distributed computing system, client computer for distributed computing, server computer for distributed computing, distributed computing method, and information recording medium |
CN103747059A (en) * | 2013-12-26 | 2014-04-23 | 华中科技大学 | Method and system for guaranteeing cloud computing server cluster network |
CN103957246A (en) * | 2014-04-22 | 2014-07-30 | 广州杰赛科技股份有限公司 | Dynamic load balancing method and system based on tenant sensing |
CN103973676A (en) * | 2014-04-21 | 2014-08-06 | 蓝盾信息安全技术股份有限公司 | Cloud computing safety protection system and method based on SDN |
CN104364763A (en) * | 2012-05-30 | 2015-02-18 | 赛门铁克公司 | Systems and methods for disaster recovery of multi-tier applications |
CN104487948A (en) * | 2012-09-07 | 2015-04-01 | 甲骨文国际公司 | System and method for workflow orchestration for use with a cloud computing environment |
US20160028587A1 (en) * | 2014-07-25 | 2016-01-28 | Cohesity, Inc. | Node discovery and cluster formation for a secondary storage appliance |
CN105323282A (en) * | 2014-07-28 | 2016-02-10 | 神州数码信息系统有限公司 | Enterprise application deployment and management system for multiple tenants |
US20160070854A1 (en) * | 2013-04-17 | 2016-03-10 | Andrew Ka-Ching WONG | Aligning and clustering sequence patterns to reveal classificatory functionality of sequences |
Family Cites Families (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CA2463006A1 (en) * | 2004-01-27 | 2005-07-27 | Wrapped Apps Corporation | On demand provisioning of web applications |
US20060075079A1 (en) | 2004-10-06 | 2006-04-06 | Digipede Technologies, Llc | Distributed computing system installation |
US7596620B1 (en) * | 2008-11-04 | 2009-09-29 | Aptana, Inc. | System and method for developing, deploying, managing and monitoring a web application in a single environment |
US20100319004A1 (en) | 2009-06-16 | 2010-12-16 | Microsoft Corporation | Policy Management for the Cloud |
US8739157B2 (en) * | 2010-08-26 | 2014-05-27 | Adobe Systems Incorporated | System and method for managing cloud deployment configuration of an application |
US20120124194A1 (en) * | 2010-11-14 | 2012-05-17 | Caroline Jacqueline Shouraboura | Method and Apparatus for Efficiently Managing Network Distance between Physical Computers in a Computing Cloud |
US9465589B2 (en) | 2011-04-05 | 2016-10-11 | Microsoft Technology Licensing, Llc | Stateful component authoring and execution |
US9336060B2 (en) | 2011-06-17 | 2016-05-10 | Microsoft Technology Licensing, Llc | Middleware services framework for on-premises and cloud deployment |
US9319286B2 (en) * | 2012-03-30 | 2016-04-19 | Cognizant Business Services Limited | Apparatus and methods for managing applications in multi-cloud environments |
US8924969B2 (en) | 2012-06-07 | 2014-12-30 | Microsoft Corporation | Virtual machine image write leasing |
CN104246740A (en) * | 2012-06-08 | 2014-12-24 | 惠普发展公司,有限责任合伙企业 | Test and management for cloud applications |
US9141432B2 (en) | 2012-06-20 | 2015-09-22 | International Business Machines Corporation | Dynamic pending job queue length for job distribution within a grid environment |
US9419859B2 (en) | 2012-12-04 | 2016-08-16 | Microsoft Technology Licensing, Llc | Service allocation in a distributed computing platform |
US9043458B2 (en) | 2013-03-19 | 2015-05-26 | Cognizant Technology Solutions India Pvt. Ltd. | Framework for facilitating implementation of multi-tenant SaaS architecture |
US9645811B2 (en) | 2013-04-01 | 2017-05-09 | Oc Acquisition Llc | Fault tolerance for a distributed computing system |
-
2016
- 2016-05-17 US US15/157,196 patent/US10153941B2/en active Active
-
2017
- 2017-05-12 EP EP17725091.7A patent/EP3458958A1/en not_active Ceased
- 2017-05-12 CN CN201780030705.XA patent/CN109196474B/en active Active
- 2017-05-12 WO PCT/US2017/032303 patent/WO2017200853A1/en unknown
Patent Citations (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20100050172A1 (en) * | 2008-08-22 | 2010-02-25 | James Michael Ferris | Methods and systems for optimizing resource usage for cloud-based networks |
US20120233315A1 (en) * | 2011-03-11 | 2012-09-13 | Hoffman Jason A | Systems and methods for sizing resources in a cloud-based environment |
CN102110041A (en) * | 2011-03-15 | 2011-06-29 | 浪潮(北京)电子信息产业有限公司 | System and method for monitoring storage space of distributed file system |
CN102915331A (en) * | 2011-09-12 | 2013-02-06 | 微软公司 | Coordination engine for cloud selection |
CN103034536A (en) * | 2011-12-12 | 2013-04-10 | 微软公司 | Usability for improving stateful applications |
US20130262556A1 (en) * | 2012-03-28 | 2013-10-03 | Microsoft Corporation | Enhanced Computer Cluster Operation Using Resource Allocation Requests |
CN102708000A (en) * | 2012-04-19 | 2012-10-03 | 北京华胜天成科技股份有限公司 | System and method for realizing energy consumption control through virtual machine migration |
CN102722413A (en) * | 2012-05-16 | 2012-10-10 | 上海兆民云计算科技有限公司 | Distributed resource scheduling method for desktop cloud cluster |
CN104364763A (en) * | 2012-05-30 | 2015-02-18 | 赛门铁克公司 | Systems and methods for disaster recovery of multi-tier applications |
US20140032531A1 (en) * | 2012-07-25 | 2014-01-30 | Cisco Technology, Inc. | System and method for a service metering framework in a network environment |
WO2014034199A1 (en) * | 2012-08-30 | 2014-03-06 | 株式会社ソニー・コンピュータエンタテインメント | Distributed computing system, client computer for distributed computing, server computer for distributed computing, distributed computing method, and information recording medium |
CN104487948A (en) * | 2012-09-07 | 2015-04-01 | 甲骨文国际公司 | System and method for workflow orchestration for use with a cloud computing environment |
US20160070854A1 (en) * | 2013-04-17 | 2016-03-10 | Andrew Ka-Ching WONG | Aligning and clustering sequence patterns to reveal classificatory functionality of sequences |
CN103747059A (en) * | 2013-12-26 | 2014-04-23 | 华中科技大学 | Method and system for guaranteeing cloud computing server cluster network |
CN103973676A (en) * | 2014-04-21 | 2014-08-06 | 蓝盾信息安全技术股份有限公司 | Cloud computing safety protection system and method based on SDN |
CN103957246A (en) * | 2014-04-22 | 2014-07-30 | 广州杰赛科技股份有限公司 | Dynamic load balancing method and system based on tenant sensing |
US20160028587A1 (en) * | 2014-07-25 | 2016-01-28 | Cohesity, Inc. | Node discovery and cluster formation for a secondary storage appliance |
CN105323282A (en) * | 2014-07-28 | 2016-02-10 | 神州数码信息系统有限公司 | Enterprise application deployment and management system for multiple tenants |
Non-Patent Citations (3)
Title |
---|
DANIEL NURMI .ETAL: "The Eucalyptus Open-Source Cloud-Computing System", 《IEEE》 * |
NAIDILA SADASHIV .ETAL: "Cluster, grid and cloud computing A detailed comparison", 《IEEE》 * |
王桂玲 等: "基于云计算的流数据集成与服务", 《计算机学报》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111124692A (en) * | 2020-01-02 | 2020-05-08 | 神州数码融信软件有限公司 | Service request processing system |
CN113905083A (en) * | 2021-10-15 | 2022-01-07 | 上海商汤临港智能科技有限公司 | User code operation method and device, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109196474B (en) | 2021-12-03 |
US20170339008A1 (en) | 2017-11-23 |
EP3458958A1 (en) | 2019-03-27 |
US10153941B2 (en) | 2018-12-11 |
WO2017200853A1 (en) | 2017-11-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109196474A (en) | Distributed operation control in computing system | |
US11768695B2 (en) | Methods and apparatus to deploy a hybrid workload domain | |
US11157304B2 (en) | System for peering container clusters running on different container orchestration systems | |
US20220377045A1 (en) | Network virtualization of containers in computing systems | |
CN105579965B (en) | Via the client guard station resources control of provider's defining interface | |
US11928506B2 (en) | Managing composition service entities with complex networks | |
US8761036B2 (en) | Network control apparatus and method with quality of service controls | |
US9288104B2 (en) | Chassis controllers for converting universal flows | |
US9130943B1 (en) | Managing communications between client applications and application resources of on-premises and cloud computing nodes | |
CN110325968A (en) | System upgrade management in distributed computing system | |
CN107534570A (en) | Virtualize network function monitoring | |
CN109313564A (en) | For supporting the server computer management system of the highly usable virtual desktop of multiple and different tenants | |
EP2815346A1 (en) | Coordination of processes in cloud computing environments | |
US20150120936A1 (en) | Coordination of processes in cloud computing environments | |
US20190319837A1 (en) | Methods and apparatus to migrate physical server hosts between virtual standard switches and virtual distributed switches in a network | |
CN109716299A (en) | Service position management in computing system | |
JP2023551841A (en) | Migrating complex legacy applications | |
US9106676B1 (en) | Grid-based server messaging infrastructure | |
US11422842B2 (en) | Virtual machine operation management in computing devices | |
Bohm et al. | PULCEO-A Novel Architecture for Universal and Lightweight Cloud-Edge Orchestration | |
US20240086221A1 (en) | Handling device configuration changes in distributed network verification application | |
Battarra et al. | Storm clouds platform: a cloud computing platform for smart city applications | |
US20220179712A1 (en) | System and method for unified infrastructure architecture | |
Steinbauer et al. | Challenges in the management of federated heterogeneous scientific clouds | |
d’Agostino et al. | An embedded low-cost solution for a fog computing device on the Internet of Things |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |